Hi. Thanks again for the wonderful work.
One thing that is extremely vague in your paper is what exactly the "Model" in Figure 1? Is is a multiple instance method? (averaging) and if yes do you have some idea one why multiple instance learning papers stating to be SOTA still get worser results than you work? (e.g. Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning and DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification)
Hi. Thanks again for the wonderful work.
One thing that is extremely vague in your paper is what exactly the "Model" in Figure 1? Is is a multiple instance method? (averaging) and if yes do you have some idea one why multiple instance learning papers stating to be SOTA still get worser results than you work? (e.g. Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning and DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification)